Automated summary
This skill exposes CLI commands to create, update, and monitor multi-step tasks that persist across restarts and are shared across every conversation thread.
Strengths
- Global tasks visible from any thread, unlike per-thread todos
- On-disk persistence at ~/.config/alma/tasks.json with automatic injection into context
- Explicit step breakdown with current-step tracking and statuses (pending, in_progress, done, blocked)
- Full lifecycle support: create, retitle, link to a thread, show details, and delete
Limitations
- Relies entirely on the external `alma` command, which the skill does not provide
- Progress is tracked by a zero-indexed step number, an easy source of off-by-one mistakes
- No notion of priority, deadlines, or dependencies between tasks
Use it whenever work spans three or more steps and needs to stay traceable across turns or after a restart.
For a one-off action or a checklist confined to a single conversation, where plain todos are enough.
Security analysis
CautionThe skill does not perform destructive, exfiltrating, or obfuscated actions; it only manages local task records through a CLI. However, it grants Bash access and writes persistent state, so it is best treated as a legitimate but powerful-tool skill requiring caution.
- •Declares Bash access and instructs execution of the `alma tasks` CLI.
- •Commands mutate persistent local state at `~/.config/alma/tasks.json`.
- •Does not explicitly warn about shell quoting/validation for user-supplied task titles or step text.
Examples
I need to add Discord chat logging to the bridge. Create a task, break it into steps, and keep it updated as you work.List my active tasks and tell me which step we were on for the People settings page.Mark the task for the People settings page as done and show me what's still blocked.name: tasks description: Global multi-step task tracking. Create, update, and monitor long-running tasks across threads. Tasks persist across restarts and are visible in all conversations. allowed-tools:
- Bash
Tasks Skill
Track complex, multi-step tasks globally. Unlike todos (per-thread), tasks are shared across ALL threads and persist across restarts.
When to Use
- Starting a complex task with 3+ steps
- User asks you to do something that will take multiple turns
- You need to track progress on ongoing work
- You want to remember what you were doing after a restart
Commands
List active tasks
alma tasks list # active tasks (default)
alma tasks list all # all tasks
alma tasks list done # completed tasks
Create a task
alma tasks add "Build People settings page"
Update a task (set steps, progress, status)
# Set steps for a task
alma tasks update <id> --steps "Design API,Build backend,Build frontend,Test,Deploy"
# Mark progress (0-indexed step number)
alma tasks update <id> --step 2 --status in_progress
# Link to current thread
alma tasks update <id> --thread <threadId>
# Change title
alma tasks update <id> --title "New title"
Mark done
alma tasks done <id>
Show details
alma tasks show <id>
Delete
alma tasks delete <id>
Status Values
pending— Created but not startedin_progress— Currently being worked ondone— Completedblocked— Waiting on something
Workflow Example
# 1. Create task when starting complex work
alma tasks add "Add Discord chat logging"
# 2. Define steps
alma tasks update t1abc --steps "Add log method to bridge,Log user messages,Log bot replies,Test,Release"
# 3. Start working
alma tasks update t1abc --status in_progress --step 0
# 4. Progress through steps
alma tasks update t1abc --step 1
alma tasks update t1abc --step 2
# 5. Complete
alma tasks done t1abc
Rules
- ALWAYS create a task when starting multi-step work (3+ steps)
- Update progress as you complete each step
- Mark done immediately when finished — don't leave stale tasks
- Keep task titles concise but descriptive
- Steps should be actionable and specific
- Clean up completed tasks periodically (or let them stay for history)
Storage
Tasks are stored at ~/.config/alma/tasks.json and injected into your context automatically. You can always see your active tasks.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/multi-step-task-tracking-mm8o51x8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/multi-step-task-tracking-mm8o51x8/download' --output '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md.part' && mv '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md.part' '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && test -s '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tasks' && cp -R '.skill-downloads/multi-step-task-tracking-mm8o51x8' '.claude/skills/tasks'Cursor
test -f '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && test -s '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/tasks' && cp -R '.skill-downloads/multi-step-task-tracking-mm8o51x8' '.cursor/skills/tasks'Codex
test -f '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && test -s '.skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/tasks' && cp -R '.skill-downloads/multi-step-task-tracking-mm8o51x8' '.agents/skills/tasks'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/multi-step-task-tracking-mm8o51x8'openskills read 'multi-step-task-tracking-mm8o51x8'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/multi-step-task-tracking-mm8o51x8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.